Add GLM 5.3 Flash support

src/server/request.rs

@@ -54,6 +54,23 @@ pub(super) fn anthropic_request(value: Value) -> Result<ChatRequest, (u16, Strin
         for block in blocks {
             match block.get("type").and_then(Value::as_str).unwrap_or("text") {
                 "text" => text.push_str(block.get("text").and_then(Value::as_str).unwrap_or("")),
+                "image" => {
+                    let source = block.get("source").and_then(Value::as_object);
+                    let media = source
+                        .and_then(|source| source.get("media_type"))
+                        .and_then(Value::as_str)
+                        .unwrap_or("");
+                    let data = source
+                        .and_then(|source| source.get("data"))
+                        .and_then(Value::as_str)
+                        .unwrap_or("");
+                    if !matches!(media, "image/png" | "image/jpeg") || data.is_empty() {
+                        return Err((400, "image input must be inline PNG or JPEG base64".into()));
+                    }
+                    text.push_str(&crate::engine::vision_data_marker(&format!(
+                        "data:{media};base64,{data}"
+                    )));
+                }
                 "thinking" | "redacted_thinking" => reasoning.push_str(
                     block
                         .get("thinking")
@@ -382,6 +399,24 @@ fn responses_content_text(value: &Value) -> Result<String, (u16, String)> {
                             text.push_str(value);
                         }
                     }
+                    Value::Object(part)
+                        if part.get("type").and_then(Value::as_str) == Some("input_image") =>
+                    {
+                        let url = part
+                            .get("image_url")
+                            .or_else(|| part.get("url"))
+                            .and_then(Value::as_str)
+                            .ok_or_else(|| (400, "invalid image input".into()))?;
+                        if !url.starts_with("data:image/png;base64,")
+                            && !url.starts_with("data:image/jpeg;base64,")
+                        {
+                            return Err((
+                                400,
+                                "image input must be an inline PNG or JPEG data URI".into(),
+                            ));
+                        }
+                        text.push_str(&crate::engine::vision_data_marker(url));
+                    }
                     _ => return Err((400, "invalid JSON request".into())),
                 }
             }
@@ -574,7 +609,12 @@ fn request_reasoning(
         || (explicit_thinking.is_none()
             && matches!(
                 model_id,
-                "deepseek-chat" | "glm-5.2-chat" | "glm-5.2-no-think" | "glm-5.2-nothink"
+                "deepseek-chat"
+                    | "glm-5.2-chat"
+                    | "glm-5.2-no-think"
+                    | "glm-5.2-nothink"
+                    | "glm-5.3-flash-chat"
+                    | "zai/glm-5.3-flash-chat"
             ))
     {
         reasoning = ReasoningMode::Direct;

src/server/tools.rs

@@ -365,6 +365,7 @@ pub(super) fn render_messages(
 
     let mut turns = Vec::<ChatTurn>::new();
     for message in messages {
+        validate_inline_images(&message.content)?;
         let content = content_text(&message.content);
         match message.role.as_str() {
             "system" | "developer" => {
@@ -426,6 +427,30 @@ pub(super) fn render_messages(
     Ok((system, turns))
 }
 
+fn validate_inline_images(value: &Value) -> Result<(), (u16, String)> {
+    let Some(parts) = value.as_array() else {
+        return Ok(());
+    };
+    for part in parts {
+        let Some(image) = part.get("image_url") else {
+            continue;
+        };
+        let url = image
+            .get("url")
+            .or(Some(image))
+            .and_then(Value::as_str)
+            .ok_or_else(|| (400, "invalid image input".into()))?;
+        if !url.starts_with("data:image/png;base64,") && !url.starts_with("data:image/jpeg;base64,")
+        {
+            return Err((
+                400,
+                "image input must be an inline PNG or JPEG data URI".into(),
+            ));
+        }
+    }
+    Ok(())
+}
+
 pub(super) fn validate_tool_results(
     state: &State,
     messages: &[ApiMessage],
@@ -779,8 +804,18 @@ pub(super) fn content_text(value: &Value) -> String {
         Value::Array(parts) => parts
             .iter()
             .filter_map(|part| match part {
-                Value::String(text) => Some(text.as_str()),
-                Value::Object(object) => object.get("text").and_then(Value::as_str),
+                Value::String(text) => Some(text.clone()),
+                Value::Object(object) => object
+                    .get("text")
+                    .and_then(Value::as_str)
+                    .map(str::to_owned)
+                    .or_else(|| {
+                        let url = object
+                            .get("image_url")
+                            .and_then(|value| value.get("url").or(Some(value)))
+                            .and_then(Value::as_str)?;
+                        Some(crate::engine::vision_data_marker(url))
+                    }),
                 _ => None,
             })
             .collect(),